HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yinghao, Qi, Yifan, Wang, Zixiang, Gu, Lei, Sui, Dehao, Hu, Haoran, Zhang, Xichen, He, Ziyi, He, Junjun, Ma, Liantao, Yu, Lequan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908586892853248
author Zhu, Yinghao
Qi, Yifan
Wang, Zixiang
Gu, Lei
Sui, Dehao
Hu, Haoran
Zhang, Xichen
He, Ziyi
He, Junjun
Ma, Liantao
Yu, Lequan
author_facet Zhu, Yinghao
Qi, Yifan
Wang, Zixiang
Gu, Lei
Sui, Dehao
Hu, Haoran
Zhang, Xichen
He, Ziyi
He, Junjun
Ma, Liantao
Yu, Lequan
contents The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current AI agents, however, are constrained by static, predefined strategies, limiting their ability to navigate the complex, evolving ecosystem of scientific research. This paper introduces HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its high-level problem-solving policies by distilling procedural successes and failures into a durable, structured knowledge base, enabling it to learn not just how to use tools, but how to strategize. To anchor our research and provide a community resource, we introduce EHRFlowBench, a new benchmark featuring complex health data analysis tasks systematically derived from peer-reviewed scientific literature. Our experiments demonstrate that HealthFlow's self-evolving approach significantly outperforms state-of-the-art agent frameworks. This work offers a new paradigm for intelligent systems that can learn to operationalize the procedural knowledge embedded in scientific content, marking a critical step toward more autonomous and effective AI for healthcare scientific discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
Zhu, Yinghao
Qi, Yifan
Wang, Zixiang
Gu, Lei
Sui, Dehao
Hu, Haoran
Zhang, Xichen
He, Ziyi
He, Junjun
Ma, Liantao
Yu, Lequan
Artificial Intelligence
Computation and Language
Machine Learning
Multiagent Systems
The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current AI agents, however, are constrained by static, predefined strategies, limiting their ability to navigate the complex, evolving ecosystem of scientific research. This paper introduces HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its high-level problem-solving policies by distilling procedural successes and failures into a durable, structured knowledge base, enabling it to learn not just how to use tools, but how to strategize. To anchor our research and provide a community resource, we introduce EHRFlowBench, a new benchmark featuring complex health data analysis tasks systematically derived from peer-reviewed scientific literature. Our experiments demonstrate that HealthFlow's self-evolving approach significantly outperforms state-of-the-art agent frameworks. This work offers a new paradigm for intelligent systems that can learn to operationalize the procedural knowledge embedded in scientific content, marking a critical step toward more autonomous and effective AI for healthcare scientific discovery.
title HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
topic Artificial Intelligence
Computation and Language
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2508.02621